How agent-ready is Square?

Square's agentability score of 37/100 on its homepage indicates significant barriers for autonomous AI agents attempting to navigate and operate the platform. The pricing page performs moderately better at 50/100, while documentation sits at 39/100. These scores suggest that while basic parsing is possible, agents will struggle with error recovery, understanding system state, and executing multi-step workflows reliably.

The audit identifies clean handoffs (0/100) and transparency (18/100) as the most critical gaps. Square also shows weakness in status communication (30/100) and defaults (33/100). Machine readability (66/100) and chunking (58/100) are relative strengths, indicating that content structure is reasonably accessible, but the lack of structured error handling and state visibility creates friction points that will cause agent failures in production scenarios.

To improve agentability, Square should prioritize the following changes:

• Return structured error responses that include what failed, the relevant error code, and the offending field in both UI and API responses, replacing generic 'Something went wrong' messages.
• Make every error state actionable by explicitly stating the next step, such as 'Email is invalid — enter a valid address' rather than only describing the problem.
• Implement confirmation steps for destructive actions using distinctly-labelled UI elements that are visually and semantically different from standard action buttons.
• Display progress for long-running tasks using an enumerated multi-step indicator or activity feed so agents can track completion status.
• Add JSON-LD structured data using schema.org vocabulary to describe primary entities on each page, improving machine parseability.
• Provide one-line summaries with expandable details for important results, and attach source references or input citations to any generated outputs.